AI-Driven Visual Inspection for Predicting Meat Freshness and Quality

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Raj, Abhishek, Vijay, B K Sai, Kundu, Sourin, Arasi, Ehzil
Format: Recurso digital
Langue:anglais
Publié: Zenodo 2025
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866902023003176960
author Raj, Abhishek
Vijay, B K Sai
Kundu, Sourin
Arasi, Ehzil
author_facet Raj, Abhishek
Vijay, B K Sai
Kundu, Sourin
Arasi, Ehzil
contents <p>ABSTRACT To make meat fresh and safe is a real issue for the food industry. A computer vision-based system with artificial intelligence methods to forecast the quality of one of the widely eaten meats in India: chicken. The suggested system takes photos of meat samples and converts them from the RGB to HSV color space in order to more effectively isolate hue, saturation, and brightness features that are indicative of spoilage and freshness. In contrast to conventional binary classification systems, this model scores meat on a scale of four classes—fresh, edible, spoiled, and toxic—to provide a more nuanced evaluation. Furthermore, the system utilizes regression models to forecast the shelf life of remaining meat and suggests proper storage conditions (e.g., refrigerate or freeze) to maintain quality. </p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17489799
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle AI-Driven Visual Inspection for Predicting Meat Freshness and Quality
Raj, Abhishek
Vijay, B K Sai
Kundu, Sourin
Arasi, Ehzil
<p>ABSTRACT To make meat fresh and safe is a real issue for the food industry. A computer vision-based system with artificial intelligence methods to forecast the quality of one of the widely eaten meats in India: chicken. The suggested system takes photos of meat samples and converts them from the RGB to HSV color space in order to more effectively isolate hue, saturation, and brightness features that are indicative of spoilage and freshness. In contrast to conventional binary classification systems, this model scores meat on a scale of four classes—fresh, edible, spoiled, and toxic—to provide a more nuanced evaluation. Furthermore, the system utilizes regression models to forecast the shelf life of remaining meat and suggests proper storage conditions (e.g., refrigerate or freeze) to maintain quality. </p>
title AI-Driven Visual Inspection for Predicting Meat Freshness and Quality
url https://doi.org/10.5281/zenodo.17489799